Complementary consistency semi-supervised learning for 3D left atrial image segmentation

TL;DR

This paper introduces CC-Net, a semi-supervised learning framework for 3D left atrial image segmentation that leverages complementary consistency and auxiliary models to improve segmentation accuracy with limited labeled data.

Contribution

The paper proposes a novel complementary consistency training method with a symmetric structure, enhancing semi-supervised segmentation by utilizing auxiliary models to focus on ambiguous regions.

Findings

CC-Net outperforms existing algorithms on two public datasets.

It achieves the best semi-supervised segmentation performance with limited labeled data.

The method effectively reduces uncertainty in decision boundaries.

Abstract

A network based on complementary consistency training, called CC-Net, has been proposed for semi-supervised left atrium image segmentation. CC-Net efficiently utilizes unlabeled data from the perspective of complementary information to address the problem of limited ability of existing semi-supervised segmentation algorithms to extract information from unlabeled data. The complementary symmetric structure of CC-Net includes a main model and two auxiliary models. The complementary model inter-perturbations between the main and auxiliary models force consistency to form complementary consistency. The complementary information obtained by the two auxiliary models helps the main model to effectively focus on ambiguous areas, while enforcing consistency between the models is advantageous in obtaining decision boundaries with low uncertainty. CC-Net has been validated on two public datasets. In the case of specific proportions of labeled data, compared with current advanced algorithms, CC-Net has the best semi-supervised segmentation performance. Our code is publicly available at https://github.com/Cuthbert-Huang/CC-Net.